© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 24388
    Prev
    Next
    INDEX
    Explanations

    components or elements within a system

    oai_token-act-pair · gpt-3.5-turbo

    words associated with components and elements of various subjects or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paces
    -1.11
    ettings
    -0.98
    scl
    -0.93
    pace
    -0.91
    poons
    -0.87
    cale
    -0.86
    creen
    -0.86
    cape
    -0.83
    hops
    -0.82
    anders
    -0.82
    POSITIVE LOGITS
    ment
    0.82
    naire
    0.81
    ially
    0.80
    uated
    0.80
    ality
    0.80
    iously
    0.78
    iator
    0.78
    atively
    0.75
    gha
    0.73
    ry
    0.71
    Activations Density 0.038%

    No Known Activations